1 files changed, 74 insertions, 111 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index a08cedefbfaa..70d9ce294bb4 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1695,8 +1695,9 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct shmem_inode_info *info = SHMEM_I(inode);
-	struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm;
-	struct page *page;
+	struct mm_struct *charge_mm = vma ? vma->vm_mm : NULL;
+	struct swap_info_struct *si;
+	struct page *page = NULL;
 	swp_entry_t swap;
 	int error;
 
@@ -1704,6 +1705,12 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 	swap = radix_to_swp_entry(*pagep);
 	*pagep = NULL;
 
+	/* Prevent swapoff from happening to us. */
+	si = get_swap_device(swap);
+	if (!si) {
+		error = EINVAL;
+		goto failed;
+	}
 	/* Look it up and read it in.. */
 	page = lookup_swap_cache(swap, NULL, 0);
 	if (!page) {
@@ -1765,6 +1772,8 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 	swap_free(swap);
 
 	*pagep = page;
+	if (si)
+		put_swap_device(si);
 	return 0;
 failed:
 	if (!shmem_confirm_swap(mapping, index, swap))
@@ -1775,6 +1784,9 @@ unlock:
 		put_page(page);
 	}
 
+	if (si)
+		put_swap_device(si);
+
 	return error;
 }
 
@@ -1785,7 +1797,7 @@ unlock:
  * vm. If we swap it in we mark it dirty since we also free the swap
  * entry since a page cannot live in both the swap and page cache.
  *
- * vmf and fault_type are only supplied by shmem_fault:
+ * vma, vmf, and fault_type are only supplied by shmem_fault:
  * otherwise they are NULL.
  */
 static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
@@ -1816,10 +1828,20 @@ repeat:
 	}
 
 	sbinfo = SHMEM_SB(inode->i_sb);
-	charge_mm = vma ? vma->vm_mm : current->mm;
+	charge_mm = vma ? vma->vm_mm : NULL;
 
 	page = pagecache_get_page(mapping, index,
 					FGP_ENTRY | FGP_HEAD | FGP_LOCK, 0);
+
+	if (page && vma && userfaultfd_minor(vma)) {
+		if (!xa_is_value(page)) {
+			unlock_page(page);
+			put_page(page);
+		}
+		*fault_type = handle_userfault(vmf, VM_UFFD_MINOR);
+		return 0;
+	}
+
 	if (xa_is_value(page)) {
 		error = shmem_swapin_page(inode, index, &page,
 					  sgp, gfp, vma, fault_type);
@@ -2227,7 +2249,7 @@ static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
 }
 #endif
 
-int shmem_lock(struct file *file, int lock, struct user_struct *user)
+int shmem_lock(struct file *file, int lock, struct ucounts *ucounts)
 {
 	struct inode *inode = file_inode(file);
 	struct shmem_inode_info *info = SHMEM_I(inode);
@@ -2239,13 +2261,13 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 	 * no serialization needed when called from shm_destroy().
 	 */
 	if (lock && !(info->flags & VM_LOCKED)) {
-		if (!user_shm_lock(inode->i_size, user))
+		if (!user_shm_lock(inode->i_size, ucounts))
 			goto out_nomem;
 		info->flags |= VM_LOCKED;
 		mapping_set_unevictable(file->f_mapping);
 	}
-	if (!lock && (info->flags & VM_LOCKED) && user) {
-		user_shm_unlock(inode->i_size, user);
+	if (!lock && (info->flags & VM_LOCKED) && ucounts) {
+		user_shm_unlock(inode->i_size, ucounts);
 		info->flags &= ~VM_LOCKED;
 		mapping_clear_unevictable(file->f_mapping);
 	}
@@ -2258,25 +2280,11 @@ out_nomem:
 static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct shmem_inode_info *info = SHMEM_I(file_inode(file));
+	int ret;
 
-	if (info->seals & F_SEAL_FUTURE_WRITE) {
-		/*
-		 * New PROT_WRITE and MAP_SHARED mmaps are not allowed when
-		 * "future write" seal active.
-		 */
-		if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE))
-			return -EPERM;
-
-		/*
-		 * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as
-		 * MAP_SHARED and read-only, take care to not allow mprotect to
-		 * revert protections on such mappings. Do this only for shared
-		 * mappings. For private mappings, don't need to mask
-		 * VM_MAYWRITE as we still want them to be COW-writable.
-		 */
-		if (vma->vm_flags & VM_SHARED)
-			vma->vm_flags &= ~(VM_MAYWRITE);
-	}
+	ret = seal_check_future_write(info->seals, vma);
+	if (ret)
+		return ret;
 
 	/* arm64 - allow memory tagging on RAM-based files */
 	vma->vm_flags |= VM_MTE_ALLOWED;
@@ -2354,36 +2362,45 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 	return inode;
 }
 
-static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
-				  pmd_t *dst_pmd,
-				  struct vm_area_struct *dst_vma,
-				  unsigned long dst_addr,
-				  unsigned long src_addr,
-				  bool zeropage,
-				  struct page **pagep)
+#ifdef CONFIG_USERFAULTFD
+int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
+			   pmd_t *dst_pmd,
+			   struct vm_area_struct *dst_vma,
+			   unsigned long dst_addr,
+			   unsigned long src_addr,
+			   bool zeropage,
+			   struct page **pagep)
 {
 	struct inode *inode = file_inode(dst_vma->vm_file);
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct address_space *mapping = inode->i_mapping;
 	gfp_t gfp = mapping_gfp_mask(mapping);
 	pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
-	spinlock_t *ptl;
 	void *page_kaddr;
 	struct page *page;
-	pte_t _dst_pte, *dst_pte;
 	int ret;
-	pgoff_t offset, max_off;
+	pgoff_t max_off;
 
-	ret = -ENOMEM;
-	if (!shmem_inode_acct_block(inode, 1))
-		goto out;
+	if (!shmem_inode_acct_block(inode, 1)) {
+		/*
+		 * We may have got a page, returned -ENOENT triggering a retry,
+		 * and now we find ourselves with -ENOMEM. Release the page, to
+		 * avoid a BUG_ON in our caller.
+		 */
+		if (unlikely(*pagep)) {
+			put_page(*pagep);
+			*pagep = NULL;
+		}
+		return -ENOMEM;
+	}
 
 	if (!*pagep) {
+		ret = -ENOMEM;
 		page = shmem_alloc_page(gfp, info, pgoff);
 		if (!page)
 			goto out_unacct_blocks;
 
-		if (!zeropage) {	/* mcopy_atomic */
+		if (!zeropage) {	/* COPY */
 			page_kaddr = kmap_atomic(page);
 			ret = copy_from_user(page_kaddr,
 					     (const void __user *)src_addr,
@@ -2393,11 +2410,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 			/* fallback to copy_from_user outside mmap_lock */
 			if (unlikely(ret)) {
 				*pagep = page;
-				shmem_inode_unacct_blocks(inode, 1);
+				ret = -ENOENT;
 				/* don't free the page */
-				return -ENOENT;
+				goto out_unacct_blocks;
 			}
-		} else {		/* mfill_zeropage_atomic */
+		} else {		/* ZEROPAGE */
 			clear_highpage(page);
 		}
 	} else {
@@ -2405,15 +2422,15 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 		*pagep = NULL;
 	}
 
-	VM_BUG_ON(PageLocked(page) || PageSwapBacked(page));
+	VM_BUG_ON(PageLocked(page));
+	VM_BUG_ON(PageSwapBacked(page));
 	__SetPageLocked(page);
 	__SetPageSwapBacked(page);
 	__SetPageUptodate(page);
 
 	ret = -EFAULT;
-	offset = linear_page_index(dst_vma, dst_addr);
 	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
-	if (unlikely(offset >= max_off))
+	if (unlikely(pgoff >= max_off))
 		goto out_release;
 
 	ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL,
@@ -2421,32 +2438,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	if (ret)
 		goto out_release;
 
-	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
-	if (dst_vma->vm_flags & VM_WRITE)
-		_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
-	else {
-		/*
-		 * We don't set the pte dirty if the vma has no
-		 * VM_WRITE permission, so mark the page dirty or it
-		 * could be freed from under us. We could do it
-		 * unconditionally before unlock_page(), but doing it
-		 * only if VM_WRITE is not set is faster.
-		 */
-		set_page_dirty(page);
-	}
-
-	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
-
-	ret = -EFAULT;
-	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
-	if (unlikely(offset >= max_off))
-		goto out_release_unlock;
-
-	ret = -EEXIST;
-	if (!pte_none(*dst_pte))
-		goto out_release_unlock;
-
-	lru_cache_add(page);
+	ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
+				       page, true, false);
+	if (ret)
+		goto out_delete_from_cache;
 
 	spin_lock_irq(&info->lock);
 	info->alloced++;
@@ -2454,50 +2449,19 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	shmem_recalc_inode(inode);
 	spin_unlock_irq(&info->lock);
 
-	inc_mm_counter(dst_mm, mm_counter_file(page));
-	page_add_file_rmap(page, false);
-	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
-
-	/* No need to invalidate - it was non-present before */
-	update_mmu_cache(dst_vma, dst_addr, dst_pte);
-	pte_unmap_unlock(dst_pte, ptl);
+	SetPageDirty(page);
 	unlock_page(page);
-	ret = 0;
-out:
-	return ret;
-out_release_unlock:
-	pte_unmap_unlock(dst_pte, ptl);
-	ClearPageDirty(page);
+	return 0;
+out_delete_from_cache:
 	delete_from_page_cache(page);
 out_release:
 	unlock_page(page);
 	put_page(page);
 out_unacct_blocks:
 	shmem_inode_unacct_blocks(inode, 1);
-	goto out;
-}
-
-int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm,
-			   pmd_t *dst_pmd,
-			   struct vm_area_struct *dst_vma,
-			   unsigned long dst_addr,
-			   unsigned long src_addr,
-			   struct page **pagep)
-{
-	return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma,
-				      dst_addr, src_addr, false, pagep);
-}
-
-int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm,
-			     pmd_t *dst_pmd,
-			     struct vm_area_struct *dst_vma,
-			     unsigned long dst_addr)
-{
-	struct page *page = NULL;
-
-	return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma,
-				      dst_addr, 0, true, &page);
+	return ret;
 }
+#endif /* CONFIG_USERFAULTFD */
 
 #ifdef CONFIG_TMPFS
 static const struct inode_operations shmem_symlink_inode_operations;
@@ -4032,8 +3996,7 @@ bool shmem_huge_enabled(struct vm_area_struct *vma)
 	loff_t i_size;
 	pgoff_t off;
 
-	if ((vma->vm_flags & VM_NOHUGEPAGE) ||
-	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
+	if (!transhuge_vma_enabled(vma, vma->vm_flags))
 		return false;
 	if (shmem_huge == SHMEM_HUGE_FORCE)
 		return true;
@@ -4096,7 +4059,7 @@ int shmem_unuse(unsigned int type, bool frontswap,
 	return 0;
 }
 
-int shmem_lock(struct file *file, int lock, struct user_struct *user)
+int shmem_lock(struct file *file, int lock, struct ucounts *ucounts)
 {
 	return 0;
 }